{"id":"W4408611426","doi":"10.1109/icaiic64266.2025.10920873","title":"Defending Against High-Intensity Adversarial Perturbations in Deep Neural Networks: A Robust Swin Transformer Approach","year":2025,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Royal Military College of Canada; University of Ottawa","funders":"","keywords":"Adversarial system; Transformer; Computer science; Artificial neural network; Artificial intelligence; Deep neural networks; Electrical engineering; Engineering; Voltage","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005189721,0.0002934215,0.0004000744,0.0004239214,0.0003524366,0.0002118621,0.001063453,0.0001858381,0.00002135695],"category_scores_gemma":[0.0002073712,0.00027664,0.0001497842,0.001541852,0.00007906508,0.0009143599,0.0002694778,0.000758979,0.000005953666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002298431,"about_ca_system_score_gemma":0.00007512015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003091189,"about_ca_topic_score_gemma":0.0001922143,"domain_scores_codex":[0.9977136,0.0001866385,0.000471808,0.0007278083,0.0002844672,0.0006156716],"domain_scores_gemma":[0.9989213,0.0002617588,0.00008541265,0.0005393151,0.00009482383,0.00009737736],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000329899,0.00006824968,0.002484882,0.00001124994,0.00002584055,0.00001250941,0.0005402078,0.9250717,0.00002591898,0.0560815,0.0001581622,0.01548683],"study_design_scores_gemma":[0.0010503,0.00001965999,0.005046428,0.00002101784,0.00001622192,0.000006233767,0.0002725238,0.9925147,0.00001796083,0.00061662,0.000139514,0.000278785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01025312,0.00005655427,0.9693204,0.001349415,0.001667113,0.0003561508,5.981738e-7,0.0003405634,0.01665606],"genre_scores_gemma":[0.8835851,0.000006835662,0.1147815,0.001035813,0.0001717641,0.00002735151,0.00001842603,0.00001476504,0.0003584928],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.873332,"threshold_uncertainty_score":0.9999686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01170617088309388,"score_gpt":0.2308150385440292,"score_spread":0.2191088676609353,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}